Marlben is a multi-agent reinforcement learning benchmark based on the NeuralMMO game engine.
Project description
Marlben is a multi-agent reinforcement learning benchmark based on the NeuralMMO game engine
Installation
https://github.com/jbr-ai-labs/marlben/wiki/Quick-Start#installation
Installation via Pip
Python3.9
is required
pip install marlben
Installation with RLlib dependencies:
pip install marlben[rllib]
Usage
https://github.com/jbr-ai-labs/marlben/wiki/Quick-Start#launching-an-environment
Examples
Examples are located in examples
folder
rllib_integration.py
demonstrates how to start learning process with default config forCorridor
envrllib
installation is required
override_config.py
demonstrates how to customize configs by inheriting from default classcustom_map_generator.py
demonstrates how to customize map generation for any environmentcustom_environment.py
demonstrates how to customize whole environment structure by overriding all building blocks of the benchmark
Wiki
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
marlben-1.0.4.tar.gz
(309.3 kB
view details)
Built Distribution
marlben-1.0.4-py3-none-any.whl
(345.3 kB
view details)
File details
Details for the file marlben-1.0.4.tar.gz
.
File metadata
- Download URL: marlben-1.0.4.tar.gz
- Upload date:
- Size: 309.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.17
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6bf8c29fee0a1b3e6f6f83d045a1bc3eaaad51bf11ce223ebb2e48a0704f5652 |
|
MD5 | b0535bad898f5ba4e410cef076a50cbf |
|
BLAKE2b-256 | ad5080a9a5e209e94583858f0f8982d629eaf5f37ef25a611ab72412cdbfad62 |
File details
Details for the file marlben-1.0.4-py3-none-any.whl
.
File metadata
- Download URL: marlben-1.0.4-py3-none-any.whl
- Upload date:
- Size: 345.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.17
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 90724794f3b6c9e2d7a64a64645a7d4877919eac5e582439cd6f394811e8b0bd |
|
MD5 | 5d670a36566d1e77fe35432d47c9dfdc |
|
BLAKE2b-256 | cd3d790d8e38566d5848781d0edb078e7d9e8a0cf6e3bf6ebde8f4cb297815cf |